Tutorial 8

set Up

library(tidyverse)
library(lubridate)
library(leaflet)
library(httpuv)

stops <- read_csv("https://datajournalism.tech/wp-content/uploads/2019/10/wichita.csv")

population_2016 <- tibble(subject_race = c("asian/pacific islander", "black", "hispanic", "other/unknown", "white"),
 num_people = c(19272, 42679, 63659, 12978, 246343)) %>% 
  mutate(subject_race = as.factor(subject_race))
center_lat <- 37.671283
center_lng <- -97.346102

Data Analysis

race <- stops %>%  
  group_by(subject_race) %>% 
  summarize(
    n = n(),
    prop = n / nrow(.)
  ) %>% 
  mutate(subject_race=as.factor(subject_race))

  stop_rate <- left_join(race,population_2016,
    by = "subject_race"
  ) %>% 
  mutate(stop_rate = n / num_people)

Data Visualizations

ggplot(stop_rate, aes(x=reorder(subject_race, stop_rate), y=stop_rate, fill=subject_race))+
  geom_bar(stat="identity")+
  coord_flip()

race <- colorFactor(c("pink", "black", "yellow", "red", "blue"), domain=c("white", "black",  "asian/pacific islander", "hispanic", "other/unknown"), ordered=TRUE)

leaflet(stops) %>%
  addProviderTiles(providers$OpenStreetMap)%>% 
  setView(lat = 37.671283, lng = -97.346102, zoom=16) %>% 
  addCircleMarkers(~lng, ~lat, popup= paste("This is a", stops$subject_race, "and", stops$subject_sex, "driver."), weight=3, radius=4, color=~race(subject_race), stroke=F, fillOpacity = 1)

## Warning in validateCoords(lng, lat, funcName): Data contains 1167 rows with
## either missing or invalid lat/lon values and will be ignored